Combining a rule-based classifier with weakly supervised learning for twitter sentiment analysis

Microblog, especially Twitter, have become an integral part of our daily life, where millions of user sharing their thoughts daily because of its short length characteristics and simple manner of expression. Monitoring and analyzing sentiments from such massive amount of twitter posts provide enormous opportunities for companies and other organizations to learn about what user think and feel about their products and services. But the ever-growing unstructured and informal user-generated posts in twitter demands sentiment analysis tools that can perform well with minimum supervision. In this paper, we propose an approach for sentiment analysis on twitter, where we combine a rule-based classifier with weakly supervised Naive-Bayes classifier. To classify the tweets sentiment, we introduce a set of rules for the rule-based classifier based on the occurrences of emoticons and sentiment-bearing words, whereas several sentiment lexicons are applied to train the Naive-Bayes classifier. We conducted our experiments based on the Stanford sentiment140 dataset. Experimental results demonstrate the effectiveness of our method over the baseline in terms of recall, precision, F1 score, and accuracy.